Optimization Based on Computational Fluid Dynamics and Machine Learning for the Performance of Diffuser-Augmented Wind Turbines with Inlet Shrouds

Abstract

A methodology that could reduce computational cost and time, combining computational fluid dynamics (CFD) simulations, neural networks, and genetic algorithms to determine a diffuser-augmented wind turbine (DAWT) design is proposed. The specific approach used implements a CFD simulation validated with experimental data, and key parameters are analyzed to generate datasets for the relevant mathematical model established with the backpropagation neural network algorithm. Then, the mathematical model is used with the non-dominant sorting genetic algorithm II to optimize the design and improve the DAWT design to overcome negative constraints such as noise and low energy density. The key parameters adopted are the diffuser’s flange height/angle, the diffuser’s length, and the rotor’s axial position. It was found that the impact of the rotor’s axial position on the power output of the DAWT is the most significant parameter, and a well-designed diffuser requires accelerating the airflow while maintaining high-pressure recovery. Introducing a diffuser can suppress the wind turbine’s noise, but if the induced tip vortex is too strong, it will have the opposite effect on the noise reduction.